爬取晨星网对各公司主要职位的分析

import urllib
import urllib.request as ur
from bs4 import BeautifulSoup
import xlrd
import jieba
from scipy.misc import imread
from wordcloud import WordCloud, STOPWORDS


list1=[]
def getHtml(url):
	headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'}
	req = urllib.request.Request(url, headers=headers)
	htmls=urllib.request.urlopen(req).read()
	return  htmls
list = []
def getinfor(url,fdata):
	print(url)
	htmls = getHtml(url)
	soup=BeautifulSoup(htmls,'lxml')
	table2 = soup.select('tr')
	for i in range(len(table2)):
		if (i % 2 == 0):
			list_data = []
			for j in table2[i].select('td'):
				list_data.append(j.get_text().strip())
			list.append(list_data)
	return list

def wordcloud():
	content = open('rm.txt', 'r', encoding='utf-8').read()
	words = jieba.cut(content, cut_all=True)
	words_split = " ".join(words)
	print(words_split)
	background_pic = imread('tree.JPG')
	word_c= WordCloud(
		width=2000,
		height=2000,
		margin=2,
		background_color='BLACK',
		mask=background_pic,
		font_path='C:WindowsFontsSTZHONGS.TTF',
		stopwords=STOPWORDS,
		max_font_size=500,
		random_state=100
	)
	word_c.generate_from_text(words_split)
	word_c.to_file('tree_1.JPG')


if __name__=='__main__':
	all_data = []
	data = xlrd.open_workbook(r'symbol.xlsx')
	table = data.sheets()[0]
	nrows = table.nrows
	for i in range(0, nrows):
		data1 = table.cell(i, 0).value
		url = 'http://insiders.morningstar.com/insiders/trading/insider-activity-data2.action?&t=XNYS:'+str(data1)+'&region=usa&culture=en-US&cur=&yc=2&tc=&title=&recordCount=143&pageIndex='
		num = 0
		for i in range(3):
			pageurl = url + str(num) + '&pageSize=50&init=false&orderBy=date&order=desc&contentOps=page_list&_=1505217377066'
			num += 1
			getHtml(pageurl)
			all_data.append(getinfor(pageurl,data1))
	name = open('rm.txt', 'w')
	for dd in all_data:
		name.write(str(dd) + '
')
	name.close()
	wordcloud()

　　一.程序运用了三个主要函数：获取url函数，获取网页文本信息函数，生成词云函数

1.

def getHtml(url)

　　应对网站的反爬虫机制，添加了'User-Agent'

2.

def getinfor(url,fdata)

　　运用Beautifulsoup函数对html进行分析，并将数据返回到主函数中，存在txt文本文件中，便于调用

3.

def wordcloud()

　　运用jieba对爬取的文本文件进行分词，并配置生成词云的图片的各属性

 

二.遇到的问题

1.爬取速度过慢

解决方法：1.运用scrapy框架进行爬取，因为该网站的反爬虫机制，需要设置自动代理ip 

# -*- coding: utf-8 -*-

import random

# Scrapy settings for wordclound project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

@setting
BOT_NAME = 'wordclound'
DEFAULT_REQUEST_HEADERS = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Language': 'zh-CN,zh;q=0.8',
    'Connection': 'keep-alive',
    'Host': 'https://xueqiu.com/'}

SPIDER_MODULES = ['wordclound.spiders']
NEWSPIDER_MODULE = 'wordclound.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'wordclound (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False



# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'wordclound.middlewares.WordcloundSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'wordclound.middlewares.WordcloundDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
#    'wordclound.pipelines.WordcloundPipeline': 300,
#}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'


# 超时设置
RETRY_ENABLED = True
RETRY_HTTP_CODES = [500, 503, 504, 400, 403, 404, 408]
RETRY_TIMES = 3

DOWNLOADER_MIDDLEWARES = {
    'scrapy.contrib.downloadermiddleware.retry.RetryMiddleware': 80,
    'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 110,
    'wordclound.middlewares.ProxyMiddleware': 100,
}
PROXIES = [
    {'ip_port': 'https://222.186.52.136:90'},
    {'ip_port': 'https://36.111.205.166:80'},
    {'ip_port': 'https://211.22.55.39:3128'},
    {'ip_port': 'https://54.223.94.193:3128'},
    {'ip_port': 'https://60.205.205.48:80'},
    {'ip_port': 'https://124.47.7.38:80'},
    {'ip_port': 'https://183.219.159.202:8123'},
]
USER_AGENTS = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
]

# ITEM_PIPELINES = {
#     'wordclound.pipelines.BossJobPipeline': 300,
# }

　　

# -*- coding: utf-8 -*-

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals
import requests
import schedule

class WordcloundSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class WordcloundDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class ProxyMiddleware(object):
    def process_request(self, request, spider):
        url = ""
        proxy = 'http://' + requests.get(url=url).content.decode()
        print("**********ProxyMiddle no pass************" + proxy)
        requests.meta['proxy'] = proxy

    def process_do(self, spider):
        do = self.process_request
        schedule.every(5).seconds.do(do)